Application of Machine Learning for Aflatoxin Detection in Corn Kernels Utilizing Open Source Datasets

#import the datasets
aflatoxin_data <- read.csv("kernel_data/spectralsignatures.csv", header = T)

#select the "SC212M x PHW79" samples
df <- subset(aflatoxin_data, aflatoxin_data$Hybrid == "SC212M x PHW79")

#Create a reference, and split as high and low contaminant 
AF_ref <- df[,c(1,3)]
AF_ref$contaminant <- ifelse(AF_ref$AF_level <= 50, "LC", "HC")
AF_ref$contaminant <- as.factor(AF_ref$contaminant)

#remove the second to forth columns
df <- df[,-c(2:4)]

#remove "stray light", which can introduce unwanted noise. Remove first 50 and last 50 wavenumber
df <- df[,-c(2:51, (ncol(df)-49):ncol(df))]

#Split datasets using the Kennard-Stone (KS) algorithm
library(caTools)
set.seed(123)
spl <- sample.split(df$kernel_number, SplitRatio = 0.8)

#reference aflatoxin
AF_ref_train <- subset(AF_ref, spl == TRUE)
AF_ref_test <- subset(AF_ref, spl == FALSE)

#SNV
df_snv_train <- subset(df_snv, spl == TRUE)
df_snv_test <- subset(df_snv, spl == FALSE)

library(mdatools)
###First derivative
plsda_d1 <- plsda(df_d1_train[,-1], AF_ref_train$contaminant, 20, cv=10)
plsda_d1 <- selectCompNum(plsda_d1, 4)
pred_plsda_d1 <- predict(plsda_d1, df_d1_test[,-1], AF_ref_test$contaminant)
print(pred_plsda_d1$misclassified[,4])

library(caret)
library(randomForest)
#SNV
#Random Forest with SNV datasets model using Hyperparameter tuning
rf_snv_train <- cbind(AF_ref_train$contaminant, df_snv_train[,-1])
names(rf_snv_train)[1] <- "contaminant"
tune_grid <- expand.grid(.mtry = c(1:10))
control <- trainControl(method = "cv", number = 10)
set.seed(123)
rf_snv_model <- train(contaminant ~ ., data = rf_snv_train, method = "rf", tuneGrid = tune_grid, trControl = control, ntree = 1000, nodesize = 1)
pred_rf_snv <- predict(rf_snv_model, newdata = df_snv_test[,-1])
print(table(pred_rf_snv, AF_ref_test$contaminant))

library(caret)
##SNV model
#Tuning the model
trainControl <- trainControl(method = "cv", number = 10)

# Define gamma values
gamma_values <- c(0.01, 0.1, 0.5, 1, 5, 10, 100)

# Convert gamma values to sigma values
sigma_values <- 1 / sqrt(2 * gamma_values)

# Define the tuning grid
tuneGrid <- expand.grid(C = c(0.5, 1, 10, 100, 1000), sigma = sigma_values)
set.seed(123)
svm_snv_model <- train(contaminant ~ ., data = rf_snv_train, 
               method = "svmRadial",
               trControl = trainControl,
               tuneGrid = tuneGrid)
pred_svm_snv <- predict(svm_snv_model, df_snv_test[,-1])
table(pred_svm_snv, AF_ref_test$contaminant)

library(caret)
library(gbm)
# Define the training control
train_control <- trainControl(method = "cv", number = 10)

# Define the hyperparameter grid
tune_grid <- expand.grid(
  n.trees = c(100, 200, 300, 500, 1000),
  interaction.depth = c(1, 3, 5),
  shrinkage = c(0.01, 0.1, 0.3),
  n.minobsinnode = c(10, 20)
)

#SNV model
set.seed(123)
gbm_snv_model <- train(
  contaminant ~ ., data = rf_snv_train,
  method = "gbm",
  trControl = train_control,
  tuneGrid = tune_grid,
  verbose = FALSE
)
pred_gbm_snv <- predict(gbm_snv_model, df_snv_test[,-1])
table(pred_gbm_snv, AF_ref_test$contaminant)